<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://vulnerability.circl.lu/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-09-28T23:22:26.914766+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>info@circl.lu</email>
  </author>
  <link href="https://vulnerability.circl.lu" rel="alternate"/>
  <generator uri="https://lkiesow.github.io/python-feedgen" version="1.0.0">python-feedgen</generator>
  <subtitle>Contains only the most 10 recent entries.</subtitle>
  <entry>
    <id>https://vulnerability.circl.lu/vuln/cve-2026-53814</id>
    <title>CVE-2026-53814 — OpenClaw &lt; 2026.5.20 - Privilege Escalation via Hook-Triggered CLI MCP Tool Authority</title>
    <updated>2026-09-28T23:22:27.289430+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> OpenClaw</p>
<p>OpenClaw before 2026.5.20 contains a privilege escalation vulnerability where hook-triggered agent runs incorrectly receive owner-scoped MCP loopback authority instead of hook-appropriate scope. Attackers with a valid hook token can exploit the /hooks/agent endpoint to cause spawned CLI runtimes to access or invoke owner-only MCP tools, potentially executing privileged actions like persistent cron state modifications.</p></div>
    </content>
    <link href="https://vulnerability.circl.lu/vuln/cve-2026-53814"/>
  </entry>
  <entry>
    <id>https://vulnerability.circl.lu/vuln/ghsa-6fvr-66p3-3qj4</id>
    <title>GHSA-6fvr-66p3-3qj4 — OpenClaw: Hook-triggered CLI runs could receive owner MCP tool authority</title>
    <updated>2026-09-28T23:22:27.289536+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> npm: openclaw</p>
<p>### Summary</p>
<p>OpenClaw hook ingress can start automated agent runs using a configured hook token. In affected releases, a hook-triggered run could select a bundled CLI backend that received owner-scoped MCP loopback authority instead of a scope appropriate for hook ingress.</p>
<p>This issue affects the boundary between hook-token automation and owner-only MCP tools. It does not affect deployments with hooks disabled.</p>
<p>### Affected configurations</p>
<p>This affects deployments where hooks are enabled, `/hooks/agent` is reachable with a valid hook token, and a bundled CLI backend can be selected for the hook-triggered run.</p>
<p>### Impact</p>
<p>A caller with the hook token could cause the spawned CLI runtime to see or call MCP tools that should have been owner-only. The practical impact depends on which MCP tools are available; the reported proof used persistent cron state as a representative owner-only action.</p>
<p>### Patched Versions</p>
<p>The first stable patched version is `2026.5.20`.</p>
<p>Fixed in the `2026.5.20` stable release.</p>
<p>### Mitigations</p>
<p>Upgrade to `openclaw@2026.5.20` or later. Keep hook tokens secret, restrict network access to hook endpoints, and disable hooks when they are not needed.</p></div>
    </content>
    <link href="https://vulnerability.circl.lu/vuln/ghsa-6fvr-66p3-3qj4"/>
  </entry>
</feed>
